© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 19309
    Prev
    Next
    INDEX
    Explanations

    keywords related to job positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tenure in professional or leadership contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.76
    kell
    -0.74
    rencies
    -0.71
    hammad
    -0.68
    ki
    -0.65
    Ze
    -0.64
     Scouts
    -0.63
     Sabha
    -0.62
    igel
    -0.62
    mber
    -0.61
    POSITIVE LOGITS
     tenure
    0.91
     reign
    0.84
    ional
    0.67
    orship
    0.66
    mination
    0.65
    mates
    0.64
    aciously
    0.63
    APH
    0.63
    acious
    0.62
     spanning
    0.62
    Activations Density 0.032%

    No Known Activations